CN114947891A - Method for detecting muscle rehabilitation condition of user by using arm ring device - Google Patents

Method for detecting muscle rehabilitation condition of user by using arm ring device Download PDF

Info

Publication number
CN114947891A
CN114947891A CN202210196720.4A CN202210196720A CN114947891A CN 114947891 A CN114947891 A CN 114947891A CN 202210196720 A CN202210196720 A CN 202210196720A CN 114947891 A CN114947891 A CN 114947891A
Authority
CN
China
Prior art keywords
signals
muscle
signal
user
electromyographic
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210196720.4A
Other languages
Chinese (zh)
Inventor
高硕�
吕瑞函
郑卓
王嘉琪
陈君亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beihang University
Original Assignee
Beihang University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beihang University filed Critical Beihang University
Priority to CN202210196720.4A priority Critical patent/CN114947891A/en
Publication of CN114947891A publication Critical patent/CN114947891A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/389—Electromyography [EMG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/22—Ergometry; Measuring muscular strength or the force of a muscular blow
    • A61B5/224—Measuring muscular strength
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/25—Bioelectric electrodes therefor
    • A61B5/251—Means for maintaining electrode contact with the body
    • A61B5/256—Wearable electrodes, e.g. having straps or bands
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/25—Bioelectric electrodes therefor
    • A61B5/279—Bioelectric electrodes therefor specially adapted for particular uses
    • A61B5/296—Bioelectric electrodes therefor specially adapted for particular uses for electromyography [EMG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/6802—Sensor mounted on worn items
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/6813—Specially adapted to be attached to a specific body part
    • A61B5/6824—Arm or wrist
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Biophysics (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Artificial Intelligence (AREA)
  • Signal Processing (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physiology (AREA)
  • Psychiatry (AREA)
  • Evolutionary Computation (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

The invention discloses a device and a method for detecting the muscular atrophy degree of a user in a motion detection mode, and further discloses a method for detecting the muscular atrophy degree of the user by adopting the device. After the required myoelectric and muscle force signals are obtained, a time period when the user moves is set and obtained by using a threshold value, and the muscle capacity grade of the user is classified by using a classification algorithm so as to obtain the muscle atrophy degree of the user, thereby obtaining the rehabilitation condition of the muscle of the user. The invention successfully completes the detection and judgment of the muscular atrophy degree of the user by combining the arm ring structure with the classification algorithm, and realizes the detection of the muscular rehabilitation condition of the patient. The structure and the algorithm of the invention have the advantages of easy realization, convenient popularization and the like. The invention is applicable to the field of disease monitoring.

Description

Method for detecting muscle rehabilitation condition of user by using arm ring device
Technical Field
The invention belongs to the field of rehabilitation state evaluation, and is used for detecting rehabilitation states of motor nerve disease patients such as Parkinson and cerebral apoplexy, in particular to a corresponding method for evaluating arm muscle rehabilitation conditions of patients by detecting movement physiological signals of the patients.
Background
With the development of rehabilitation medicine in recent years, more and more attention is paid to the detection of the rehabilitation state of a patient in the rehabilitation training process. In many application scenarios, the motor physiological signals of the patient need to be detected so as to better determine the rehabilitation state of the patient, and a personalized rehabilitation scheme is formulated to achieve the purpose of promoting the rehabilitation process of the patient.
In recent years, researchers at home and abroad try to detect motion physiological signals of patients during motion so as to determine the development condition of the rehabilitation process of the patients. The patent with the publication number CN110200646A realizes quantitative measurement of muscle strength by fixing the limb of the user with a specific device to detect the pressure when the muscle to be measured exerts force, so as to determine whether the force exerted by the user meets the requirement. In patent No. CN104107134B, the patient participates in virtual game training, detects the upper limb movement signal and myoelectric signal of the patient during the game, analyzes the muscle fatigue state, and realizes the alarm of the muscle fatigue state. Both of these devices use a non-invasive method to detect the muscle condition of a patient, but both of them must be measured in a hospital, and have the problems of large volume, complicated detection process and poor portability. A wearable multi-channel electromyographic signal acquisition arm ring is disclosed in an authorized patent CN103315737B, so that the portability of the device is greatly improved, and the detection environment of a patient is not limited. However, the invention only detects the surface electromyogram signal, does not further analyze the acquired signal, and lacks the detection of other signals of muscle movement, so that the connection between other motor physiological signals of the patient and the detected surface electromyogram signal cannot be known, and the basis for judging the rehabilitation process of the patient is difficult to provide.
The existing method has the problems of poor portability and complex measuring process. Therefore, those skilled in the art have been devoted to developing a convenient device for detecting the progress of rehabilitation of neuromuscular meat diseases.
Disclosure of Invention
In order to solve the problems existing in the existing motor nerve disease rehabilitation condition detection, the invention aims to provide the wearable arm ring device capable of detecting the myoelectric signal and the myoelectric signal on the surface of a user and the using method thereof.
The invention is realized by the following technical scheme.
The invention relates to an arm ring for evaluating the muscle atrophy degree of a patient, which comprises:
the myoelectricity acquisition module is a multi-channel myoelectricity acquisition electrode. Each channel is a myoelectricity collecting electrode, and the output of the myoelectricity collecting electrode is connected with the myoelectricity signal processing circuit module.
And the muscle strength acquisition module is a multi-channel muscle strength acquisition electrode. The muscle strength collecting electrode is connected with the muscle strength signal processing circuit module.
And the electromyographic signal processing circuit module is used for processing the acquired electromyographic signals. The signal that the flesh electricity collection module gathered is exported to first order amplifier circuit, after first order amplifier circuit amplification, passes through first order filter circuit and carries out high pass filtering to the flesh electricity signal, sends into the second filter circuit afterwards and carries out low pass filter circuit in order to get rid of the interference of high frequency noise, sends into analog to digital converter through the multiplexer after 50Hz trapped wave is in order to get rid of the power frequency interference.
The muscle strength signal circuit processing module comprises an amplifying circuit and a low-pass filter circuit and is used for processing the collected muscle strength signals.
And the multiplexer is used for controlling the working process of the system and sending the physiological information acquired by the acquisition module to the analog-to-digital conversion module.
And the microcontroller is used for controlling the working process of the multiplexer and communicating the surface electromyographic signals and the muscle strength signals with the upper computer.
And the analog-to-digital converter is used for converting the surface electromyographic signals and the muscle strength signals sent by the multiplexer into digital signals and sending the converted digital signals to the input end of the microprocessor.
And the upper computer is used for receiving myoelectric and muscle force signals sent by the micro-control unit and is used for subsequent judgment of the rehabilitation condition of the patient.
Furthermore, the myoelectric signal processing circuit module, the muscle strength signal processing circuit module, the multiplexer, the analog-to-digital converter and the microcontroller are integrated on a PCB circuit board.
Furthermore, the muscle force collecting electrodes and the myoelectricity collecting electrodes have the same channel number, and the number is not less than 8.
Further, the external dimensions of the muscle force sensor module and the PCB circuit board are the same.
Furthermore, muscle strength acquisition electrode and flesh electricity acquisition electrode with the PCB circuit board is connected, contacts with patient's skin during the use.
Furthermore, the muscle force collecting electrodes and the myoelectricity collecting electrodes are distributed on the arm ring in parallel at equal intervals.
The invention further provides a using method of the arm ring device, which comprises the following steps:
the first step is as follows: the method comprises the steps of collecting original electromyographic signals, generating surface electromyographic signals on the surface of skin when the arm of a user moves, collecting the signals by a dry electrode, outputting the signals to a first-stage amplifying circuit, amplifying the signals by the first-stage amplifying circuit, carrying out high-pass filtering on the electromyographic signals by a first-stage filtering circuit, sending the signals to a second-stage filtering circuit to carry out low-pass filtering to remove interference of high-frequency noise, carrying out 50Hz trap to remove power frequency interference, sending the signals to an analog-to-digital converter by a multiplexer through the second-stage amplifying circuit to convert the analog signals into digital signals, sending the digital signals to a microcontroller, and communicating with an upper computer. The upper computer thus obtains the raw electromyographic signal semg(s).
The second step is that: the original muscle force signal is collected, when the user moves the arm, the shape of the flexible electrode in contact with the skin is changed due to the muscle force, and the signal can reflect the force applying condition of the muscle of the user. The resistance value of the flexible electrode changes after the flexible electrode is stressed, so that the partial pressure of the electrode changes, the voltage signal is amplified by the amplifying circuit and then is subjected to noise interference removal by the low-pass filter circuit, then the signal is sent to the analog-to-digital converter through the multiplexer, the analog signal is converted into a digital signal and then is sent to the microcontroller, and the microcontroller is communicated with an upper computer. Thus, the upper computer obtains an original muscle force signal FMG(s).
The third step: obtaining signal characteristics from the raw electromyographic signals, segmenting the raw semg(s) signals, adding a time stamp to each activity segment
Figure BDA0003527371190000031
Wherein i is the number of channels, i is 1,2, l, n is the number of the sEMG activity in the collection time, the effective period of muscle activity is marked, and the formula is adopted
Figure BDA0003527371190000032
Calculating to obtain the root mean square value of sEMG(s), wherein Data [ a ]]For an electromyographic data value at a certain point, interval grouping is carried out on the collected sEMG signals on a time domain, an average value in a time domain interval is calculated, and the root mean square value and the average value are used as a feature vector of the electromyographic signals of the user and recorded as a feature vector
Figure BDA0003527371190000033
Wherein
Figure BDA0003527371190000034
The root mean square value during the first validity period,
Figure BDA0003527371190000035
the average value in the first effective time interval is n, the number of the average values of the electromyographic signals and the number of root mean square values, namely the number of active sections of semg(s), i is the number of channels, and i is 1, 2.
The fourth step: obtaining signal characteristics from the raw muscle force signals, setting a threshold on the collected raw muscle force signals to obtain the muscle force signals within the activity segments, and adding a time stamp to each activity segment
Figure BDA0003527371190000036
Wherein i is the number of channels, i is 1,2, and l, m is the number of active segments of the muscle strength signal in the acquisition time. Calculating the average value in each active segment according to the formula
Figure BDA0003527371190000037
As a feature vector of the muscle strength signal of the user, is recorded as
Figure BDA0003527371190000038
Wherein
Figure BDA0003527371190000039
The root mean square value during the first validity period,
Figure BDA00035273711900000310
the average value in the first effective time interval is m, which is the number of the average value of the muscle force signals and the number of root mean square values, namely the number of muscle activity sections, i is the number of channels, and i is 1, 2.
The fifth step: because the root mean square value of the sEMG and the FMG has a relation similar to a linear function, unitary linear fitting is carried out on the root mean square value of the sEMG and the FMG in each active segment of the channel, and the relation is fitted into
Figure BDA00035273711900000311
Wherein i is the number of channels, i is 1, 2., l,
Figure BDA00035273711900000312
is the root mean square value of the sEMG,
Figure BDA00035273711900000313
is the root mean square value of the FMG.
And a sixth step: a training sample set is constructed and is used,training sample set is constructed by combining myoelectricity and muscle force signal feature vectors with linear fitting parameters
Figure BDA00035273711900000314
Taking the muscle strength grade as a training result, namely (y ═ y- 1 ,y 2 ,...,y j ) Wherein y is j In order to output a result, j is 1.
This step was performed in the following order.
For training samples, two classification problems are established first, and optimization problems need to be considered
Figure BDA00035273711900000315
And the dual problem
Figure BDA0003527371190000041
Wherein alpha is an introduced Lagrange multiplier to obtain a solution
Figure BDA0003527371190000042
To construct an optimal decision function for an SVM
Figure BDA0003527371190000043
Wherein
Figure BDA0003527371190000044
An optimal solution to the problem is optimized for unit i,
Figure BDA0003527371190000045
is the optimal solution of the unit i dual problem, C is a penalty function, ζ i For the introduced relaxation variable, w is the slope of the line divided to establish the two classification problems, b is a constant, x z Deriving the dual problem for introducing Lagrangian i Dual value of (a), y z Deriving the dual problem for introducing Lagrangian i The dual value of (c).
As a multi-classification problem, in the judgment of the muscle response ability of the user, the number of the classes j 1.M, regarding the jth class as '1' and regarding the other classes as '-1', constructing M two-classification decision functions f by using an SVM method i ＝sgn(g j (x) In which g) is j (x) A decision function for finding an optimal solution for each classification level,
Figure BDA0003527371190000046
to obtain the optimal solution. By X i In g 1 (x),...,g M (x) And judging the muscle response capability grade by judging whether the median value is maximum or not so as to obtain the judgment of the arm muscle atrophy condition of the user and further obtain the muscle rehabilitation condition of the patient.
Due to the adoption of the technical scheme, compared with the prior art, the invention has the technical progress that:
1. the invention judges the muscle rehabilitation degree of the user by introducing a multi-classification algorithm and combining the surface electromyogram signal and the muscle strength signal, and the algorithm principle and the application method have the advantages of easy realization, convenient popularization and the like, and have creativity in the field of patient rehabilitation condition evaluation.
2. Belongs to non-invasive measurement, does not cause wound, does not limit the signal detection place, and does not influence the daily life of a patient.
3. The method provided by the invention can be used for evaluating the rehabilitation status of patients with chronic neurological diseases, and the muscle strength signal and the surface myoelectric signal are jointly analyzed.
4. The invention also provides an arm ring type structure, which can simultaneously detect the surface myoelectric signal and the muscle strength signal and further analyze the relevance between the two motion physiological signals and the muscle rehabilitation condition of a patient, and the structure can also be applied to the field of motion physiological signal detection.
5. The measuring device and the processing circuit are integrated in an arm ring, can be worn for a long time, and have small influence on the daily life of a patient.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention:
fig. 1 is a schematic block diagram of embodiment 1 of the present invention.
Fig. 2 is a data acquisition flowchart of embodiment 1 of the present invention.
Fig. 3 is a diagram of original signals in embodiment 1 of the present invention.
Fig. 4 is a block diagram of an algorithm structure in embodiment 2 of the present invention.
Reference signs
11: the myoelectric acquisition unit 12: muscle strength acquisition unit
13: the myoelectric signal processing circuit 14: muscle force signal processing circuit
15: the multiplexer 16: analog-to-digital converter
17: the microprocessor 18: upper computer
17: the microprocessor 18: upper computer
21: myoelectric collection electrode 18: muscle strength collecting electrode
31: electromyogram signal data graph 31: muscle force signal data curve diagram
Detailed Description
The technical solutions of the embodiments of the present invention are further described below with reference to the accompanying drawings. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The specific steps of the method of use are described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the present embodiment includes 11 myoelectricity collecting modules, which are multi-channel myoelectricity collecting electrodes. Each channel is a myoelectricity collecting electrode, and the output of the myoelectricity collecting electrode is connected with the myoelectricity signal processing circuit module. 12 muscle strength acquisition modules, which are multi-channel muscle strength acquisition electrodes. The muscle strength collecting electrode is connected with the muscle strength signal processing circuit module. And the electromyographic signal processing circuit module 13 is used for processing the acquired electromyographic signals. And the 14 muscle force signal circuit processing module comprises an amplifying circuit and a low-pass filter circuit and is used for processing the collected muscle force signals. And the multiplexer 15 is used for controlling the working process of the system and sending the physiological information acquired by the acquisition module to the analog-to-digital conversion module. And the 16 analog-to-digital converter is used for converting the surface electromyographic signals and the muscle strength signals sent by the multiplexer into digital signals and sending the converted digital signals to the input end of the microprocessor. And the microcontroller 17 is used for controlling the working process of the multiplexer and communicating the surface electromyogram signal and the muscle strength signal with an upper computer. And the 18 upper computer is used for receiving myoelectric and muscle force signals and is used for subsequent rehabilitation condition judgment of patients.
As shown in fig. 2, for the surface electromyogram signal, the signal acquired by the electromyogram acquisition module is output to a first-stage amplification circuit, amplified by the first-stage amplification circuit, subjected to high-pass filtering by a first-stage filter circuit, then sent to a second-stage filter circuit to be subjected to low-pass filtering to remove interference of high-frequency noise, subjected to 50Hz notch to remove power frequency interference, and sent to an analog-to-digital converter by a multiplexer through the second-stage amplification circuit. A graph of electromyographic signal data is shown in fig. 31. For muscle force signals, after the signals are amplified, a low-pass filter circuit is used for filtering noise interference. The muscle force signal data plot is shown in fig. 32. The multiplexer is controlled by the microcontroller to send data to the analog-to-digital converter.
The structural block diagram of the algorithm is shown in fig. 3 and is performed according to the following steps.
The first step is as follows: obtaining signal characteristics from the raw electromyographic signals, segmenting the raw semg(s) signals, adding a time stamp to each activity segment
Figure BDA0003527371190000061
Wherein i is the number of channels, i is 1,2, and l, n is the number of sEMG activity within the collection time, marking the effective period of muscle activity, according to the formula
Figure BDA0003527371190000062
Calculating to obtain a root mean square value of sEMG(s), carrying out interval grouping on the collected sEMG signals on a time domain, calculating an average value in a time domain interval, taking the root mean square value and the average value as a user electromyographic signal feature vector together, and recording as the user electromyographic signal feature vector
Figure BDA0003527371190000063
Wherein
Figure BDA0003527371190000064
The root mean square value during the first validity period,
Figure BDA0003527371190000065
the average value in the first effective time interval is n, the number of the average values of the electromyographic signals and the number of root mean square values, namely the number of active sections of semg(s), i is the number of channels, and i is 1, 2.
The second step is that: obtaining signal characteristics from the raw muscle force signals, setting a threshold on the collected raw muscle force signals to obtain the muscle force signals within the activity segments, and adding a time stamp to each activity segment
Figure BDA0003527371190000066
Wherein i is the number of channels, i is 1,2, and l, m is the number of active segments of the muscle strength signal in the acquisition time. Calculating the average value in each active segment according to the formula
Figure BDA0003527371190000067
As a feature vector of the muscle strength signal of the user, is recorded as
Figure BDA0003527371190000068
Wherein
Figure BDA0003527371190000069
The root mean square value during the first validity period,
Figure BDA00035273711900000610
the average value in the first effective time interval is m, which is the number of the average value of the muscle force signals and the number of root mean square values, namely the number of muscle activity sections, i is the number of channels, and i is 1, 2.
The third step: because the root mean square value of the sEMG and the FMG has a relation similar to a linear function, unitary linear fitting is carried out on the root mean square value of the sEMG and the FMG in each active segment of the channel, and the relation is fitted into
Figure BDA00035273711900000611
Wherein i is the number of channels, i is 1, 2., l,
Figure BDA00035273711900000612
is the root mean square value of the sEMG,
Figure BDA00035273711900000613
is the root mean square value of the FMG.
Fourthly, constructing a training sample set, and combining the feature vectors of the myoelectricity and muscle force signals with linear fitting parameters to construct the training sample set
Figure BDA00035273711900000614
Taking muscle strength grade as a training result y ═ y 1 ,y 2 ,...,y j ) Wherein y is j In order to output a result, j is 1.
For training samples, two classification problems are established first, and optimization problems need to be considered
Figure BDA0003527371190000071
And the dual problem
Figure BDA0003527371190000072
Wherein alpha is an introduced Lagrange multiplier to obtain a solution
Figure BDA0003527371190000073
To construct an optimal decision function for an SVM
Figure BDA0003527371190000074
Wherein
Figure BDA0003527371190000075
An optimal solution to the problem is optimized for unit i,
Figure BDA0003527371190000076
is the optimal solution of the unit i dual problem, C is a penalty function, ζ i For the introduced relaxation variables, w is the slope of the line divided to establish the two classification problems, b is a constant, x z Deriving the dual problem for introducing lagrangian i Dual value of (a), y z Deriving the dual problem for introducing Lagrangian i The dual value of (c).
In the judgment of the muscle response capability of the user, as a multi-classification problem, regarding the class j as 1, the j-th class can be regarded as 1, and the other classes can be regarded as-1, and M two-classification decision functions f are constructed by using an SVM method i ＝sgn(g j (x) In which g) is j (x) A decision function for finding an optimal solution for each classification level,
Figure BDA0003527371190000077
to obtain the optimal solution. By X i In g 1 (x),...,g M (x) And judging the muscle response capability grade by judging whether the median value is maximum or not so as to obtain the judgment of the arm muscle atrophy condition of the user and further obtain the muscle rehabilitation condition of the patient.

Claims (6)

1. An arm ring capable of being used for motor nerve disease rehabilitation stage detection, which is characterized by comprising;
and the myoelectricity acquisition module is a multi-channel myoelectricity acquisition electrode. Each channel is a myoelectricity collecting electrode, and the output of the myoelectricity collecting electrode is connected with the myoelectricity signal processing circuit module;
and the muscle strength acquisition module is a multi-channel muscle strength acquisition electrode. The muscle strength acquisition electrode is connected with the muscle strength signal processing circuit module;
and the electromyographic signal processing circuit module is used for processing the acquired electromyographic signals. The method comprises the steps that signals collected by a myoelectricity collecting module are output to a first-stage amplifying circuit, are amplified by the first-stage amplifying circuit, then are subjected to high-pass filtering by a first-stage filtering circuit, are sent to a second-stage filtering circuit to be subjected to low-pass filtering so as to remove interference of high-frequency noise, are subjected to 50Hz wave trapping so as to remove power frequency interference, and are sent to an analog-digital converter by a multiplexer through the second-stage amplifying circuit;
the muscle force signal circuit processing module comprises an amplifying circuit and a low-pass filter circuit and is used for processing the collected muscle force signals;
the multiplexer is used for controlling the working process of the system and sending the physiological information acquired by the acquisition module to the analog-to-digital conversion module;
the analog-to-digital converter is used for converting the surface electromyographic signals and the muscle strength signals sent by the multiplexer into digital signals and sending the converted digital signals to the input end of the microprocessor;
the microcontroller is used for controlling the working process of the multiplexer and communicating the surface electromyographic signals and the muscle strength signals with the upper computer;
and the upper computer is used for receiving myoelectric and muscle force signals sent by the micro-control unit and is used for subsequent judgment of the rehabilitation condition of the patient.
2. The use method of the arm ring for judging the muscle atrophy degree is characterized by comprising the following steps;
the first step is as follows: the method comprises the steps of collecting original electromyographic signals, generating surface electromyographic signals on the surface of skin when the arm of a user moves, collecting the signals by a dry electrode, outputting the signals to a first-stage amplifying circuit, amplifying the signals by the first-stage amplifying circuit, carrying out high-pass filtering on the electromyographic signals by a first-stage filtering circuit, sending the signals to a second-stage filtering circuit to carry out low-pass filtering to remove interference of high-frequency noise, carrying out 50Hz trap wave to remove power frequency interference, sending the signals to an analog-to-digital converter by a multiplexer through the second-stage amplifying circuit to convert the analog signals into digital signals, sending the digital signals to a microcontroller, and communicating with an upper computer. Thus, the upper computer obtains an original electromyographic signal sEMG(s);
the second step is that: the original muscle force signal is collected, when the user moves the arm, the shape of the flexible electrode in contact with the skin is changed due to the muscle force, and the signal can reflect the force applying condition of the muscle of the user. The resistance value of the flexible electrode is changed due to deformation of the flexible electrode, noise interference is removed through the low-pass filter circuit after the flexible electrode is amplified through the amplifying circuit, then the signal is sent to the analog-to-digital converter through the multiplexer, the analog signal is converted into a digital signal, and then the digital signal is sent to the microcontroller to communicate with an upper computer. Obtaining an original muscle force signal FMG(s) by the upper computer;
the third step: acquiring signal characteristics from the original electromyographic signals, segmenting the original sEMG(s) signals, reserving the effective period of muscle activity, and obtaining the signal characteristics according to a formula
Figure FDA0003527371180000021
Calculating to obtain a root mean square value of sEMG(s), carrying out interval grouping on the collected sEMG signals on a time domain, calculating an average value in a time domain interval, taking the root mean square value and the average value as a user electromyographic signal feature vector together, and recording as the user electromyographic signal feature vector
Figure FDA0003527371180000022
Wherein
Figure FDA0003527371180000023
Root mean square value, x 'in the first effective period' 1 i The average value in the first effective time interval is n, the number of the average values of the electromyographic signals and the number of root mean square values are n, i is the number of channels, and i is 1,2, … and l;
the fourth step: acquiring signal characteristics from an original muscle force signal, setting a threshold value for the acquired original muscle force signal to acquire a muscle force signal in response, performing interval grouping on the acquired FMG signal on a time domain, calculating an average value in a time domain interval as a user muscle force signal characteristic vector, and recording the average value as a user muscle force signal characteristic vector
Figure FDA0003527371180000024
Wherein m is the number of the average value of the muscle strength signals, i is the number of channels, and i is 1,2, …, l;
the fifth step: constructing a training sample set, and constructing the training sample set by the feature vectors of the myoelectricity and muscle strength signals
Figure FDA0003527371180000025
Taking the muscle strength grade as a training result, namely (y ═ y- 1 ,y 2 ,...,y j ) Wherein y is j And j is 1, …, and M performs classification training on the training sample set by using a multi-classification method of SVM to judge the muscle response capability of the user.
3. The armlet of claim 1, wherein the electromyographic signal processing circuitry module, the muscle strength signal processing circuitry module, the multiplexer, the analog-to-digital converter, and the microcontroller are integrated on a PCB circuit board.
4. The arm ring of claim 1, wherein the muscle force collecting electrodes and the myoelectricity collecting electrodes have the same number of channels, and the number of the channels is not less than 8.
5. The arm ring of claim 1, wherein the muscle force and electromyography acquisition electrodes are connected to the PCB circuit board and, in use, contact the skin of the patient.
6. The arm ring of claim 1, wherein the muscle force collecting electrodes and the myoelectricity collecting electrodes are arranged on the arm ring in parallel and at equal intervals.
CN202210196720.4A 2022-03-02 2022-03-02 Method for detecting muscle rehabilitation condition of user by using arm ring device Pending CN114947891A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210196720.4A CN114947891A (en) 2022-03-02 2022-03-02 Method for detecting muscle rehabilitation condition of user by using arm ring device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210196720.4A CN114947891A (en) 2022-03-02 2022-03-02 Method for detecting muscle rehabilitation condition of user by using arm ring device

Publications (1)

Publication Number Publication Date
CN114947891A true CN114947891A (en) 2022-08-30

Family

ID=82975886

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210196720.4A Pending CN114947891A (en) 2022-03-02 2022-03-02 Method for detecting muscle rehabilitation condition of user by using arm ring device

Country Status (1)

Country Link
CN (1) CN114947891A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115736955A (en) * 2022-11-04 2023-03-07 海宁树健科技有限公司 System for evaluating degree of disuse muscular atrophy after skeletal joint injury based on surface myoelectricity

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115736955A (en) * 2022-11-04 2023-03-07 海宁树健科技有限公司 System for evaluating degree of disuse muscular atrophy after skeletal joint injury based on surface myoelectricity

Similar Documents

Publication Publication Date Title
CN105769173B (en) A kind of cardioelectric monitor system with electrocardiosignal noise removal function
CN108392211B (en) Fatigue detection method based on multi-information fusion
CN107041743B (en) Real-time R wave detection method for electrocardiosignals
CN104173043A (en) Electrocardiogram (ECG) data analysis method suitable for mobile platform
CN107212883B (en) A kind of mechanical arm writing device and control method based on brain electric control
CN110338790B (en) Flexible fingerstall for collecting surface myoelectricity and various physiological parameters
CN201150714Y (en) Nerve signal processing and transferring system
CN107822629A (en) The detection method of extremity surface myoelectricity axle
CN101449971A (en) Portable cardiac diagnosis monitoring device based on rhythm mode
CN114587388A (en) Neural motor function auxiliary diagnosis arm ring based on sensor space-time fusion model and use method thereof
CN114947891A (en) Method for detecting muscle rehabilitation condition of user by using arm ring device
CN113100776B (en) Fatigue monitoring system and method for fusing myoelectricity and electrocardiosignal
CN204744156U (en) Guardianship device based on wireless biomedical sensing
CN214434253U (en) Recovered wearing formula equipment of upper limbs and system
CN111053555B (en) Terrain classification device and method based on surface electromyogram signals and plantar force
Zhou et al. Design of a wireless multi-channel surface EMG signal acquisition system
CN212307837U (en) Limb movement information acquisition system based on surface myoelectricity and bioelectrical impedance
CN201200408Y (en) Lie detector with function for detecting brain electricity
CN213758282U (en) Surface electromyogram signal acquisition device
CN203208022U (en) Electroencephalograph
CN203208024U (en) Brain wave training instrument
CN115089199A (en) Patient rehabilitation state detection device and method based on surface electromyogram signal compensation
Song et al. Design of a Wireless Distributed Real-time Muscle Fatigue Detection System
CN218852715U (en) Eight-lead myoelectricity acquisition system
CN109805912A (en) The multi signal synchronous acquisition device and method of a kind of human Body Physiology Multi-parameter and inertial signal

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination